Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3820 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 4.8636. Min Range: -4.8636

Max Act: 4.8636. Min Act: -0.0000

Data Index: 244776 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 4.8636. Min Range: -4.8636

Max Act: 4.6014. Min Act: -0.0000

Data Index: 362620 (The Pile)

Max Activating Token Index: 364

Text #2

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.8169. Min Act: -0.0000

Data Index: 1383241 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.5426. Min Act: -0.0000

Data Index: 1906706 (The Pile)

Max Activating Token Index: 549

Text #4

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.4557. Min Act: -0.0000

Data Index: 1306306 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.2702. Min Act: -0.0000

Data Index: 844322 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.5413. Min Act: -0.0000

Data Index: 509594 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.0073. Min Act: -0.0000

Data Index: 997807 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.2710. Min Act: -0.0000

Data Index: 442650 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.0250. Min Act: -0.0000

Data Index: 1832783 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.0369. Min Act: -0.0000

Data Index: 1487387 (The Pile)

Max Activating Token Index: 761

Text #11

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.1252. Min Act: -0.0000

Data Index: 239335 (The Pile)

Max Activating Token Index: 607

Text #12

Max Range: 4.8636. Min Range: -4.8636

Max Act: 2.9633. Min Act: -0.0000

Data Index: 1997573 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.0531. Min Act: -0.0000

Data Index: 1611339 (The Pile)

Max Activating Token Index: 366

Text #14

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.1099. Min Act: -0.0000

Data Index: 449365 (The Pile)

Max Activating Token Index: 43

Text #15

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.0655. Min Act: -0.0000

Data Index: 961353 (The Pile)

Max Activating Token Index: 551

Text #16

Max Range: 4.8636. Min Range: -4.8636

Max Act: 2.8536. Min Act: -0.0000

Data Index: 575635 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.1710. Min Act: -0.0000

Data Index: 1254293 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 4.8636. Min Range: -4.8636

Max Act: 3.0451. Min Act: -0.0000

Data Index: 631194 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 4.8636. Min Range: -4.8636

Max Act: 2.9785. Min Act: -0.0000

Data Index: 139205 (The Pile)

Max Activating Token Index: 443